Methods of Prognostic Analysis for the Prediction of In-Hospital Mortality in Patients with Acute ST-Elevation Myocardial Infarction after Percutaneous Coronary Interventions

The aim of this study was to develop an explainable machine learning model for predicting in-hospital mortality (IHF) in patients with ST-elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI). We analyzed data from 4681 electronic medical records of patients with STEMI and identified 12 risk factors for IHF. The predictive models were developed based on multivariate logistic regression, random forest, and stochastic gradient boosting methods. The search for threshold values on the grid while maximizing the area under the ROC-curve and their validation by Shapley’s additive explanation method made it possible to verify the risk factors for IHF. The model, whose parameters were risk factors, was superior in accuracy to the best model with continuous predictors based on stochastic gradient boosting. The use of IHF risk factors as predictors makes it possible to explain the obtained prognosis and reduce the risk of adverse events after PCI.